Open main menu
Blog HomePlatformGithub

Research Paper

Reflexion: Language Agents with Verbal Reinforcement Learning
Prompt Engineering
•

Reflexion: Language Agents with Verbal Reinforcement Learning

LLM Critics Help Catch LLM Bugs
Evaluation
•

LLM Critics Help Catch LLM Bugs

LMPT: Prompt Tuning with Class-Specific Embedding Loss for Long-tailed Multi-Label Visual Recognition
Prompt Engineering
•

LMPT: Prompt Tuning with Class-Specific Embedding Loss for Long-tailed Multi-Label Visual Recognition

Soft Prompt Tuning for Augmenting Dense Retrieval with Large Language Models
Prompt Engineering
•

Soft Prompt Tuning for Augmenting Dense Retrieval with Large Language Models

MedPromptExtract (Medical Data Extraction Tool): Anonymization and Hi-fidelity Automated data extraction using NLP and prompt engineering
Prompt Engineering
•

MedPromptExtract (Medical Data Extraction Tool): Anonymization and Hi-fidelity Automated data extraction using NLP and prompt engineering

Assessing Prompt Injection Risks in 200+ Custom GPTs
Safety
•

Assessing Prompt Injection Risks in 200+ Custom GPTs

Reprompting: Automated Chain-of-Thought Prompt Inference Through Gibbs Sampling
Reasoning
•

Reprompting: Automated Chain-of-Thought Prompt Inference Through Gibbs Sampling

RNNs are not Transformers (Yet): The Key Bottleneck on In-context Retrieval
RAG
•

RNNs are not Transformers (Yet): The Key Bottleneck on In-context Retrieval

State of What Art? A Call for Multi-Prompt LLM Evaluation
Evaluation
•

State of What Art? A Call for Multi-Prompt LLM Evaluation

Prompt Cache: Modular Attention Reuse for Low-Latency Inference
Evaluation
•

Prompt Cache: Modular Attention Reuse for Low-Latency Inference